baoyu-comic

Generate multi-page knowledge comics from source content using prompt-based image generation.

6|1|Updated May 11, 2026
One-click install
npx skills add https://github.com/yakeworld/Synthos --skill baoyu-comic-yakeworld
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-comic
Source: https://github.com/yakeworld/Synthos/tree/main/skills/extended/external-automation/creative/image-art/baoyu-comic
Command: npx skills add https://github.com/yakeworld/Synthos --skill baoyu-comic-yakeworld

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning articles, biographies, or tutorials into engaging educational comics requires coordinating storyboarding, character design, prompt writing, and image generation, which is slow and inconsistent when done manually. ## Core Features & Use Cases - End-to-End Comic Workflow: Analyzes source content, builds a storyboard and character definitions, writes per-page image prompts, and generates pages via the image_generate tool. - Style System: Six art styles, seven tones, seven layouts, and five presets (ohmsha, wuxia, shoujo, concept-story, four-panel) with a content-signal auto-selection matrix. - Character Consistency: Embeds text character descriptions inline in every page prompt, with an optional character reference sheet for human review. - Use Case: Provide a biography of Alan Turing and receive a 10-page ohmsha-style educational comic with storyboard, prompts, and downloaded PNG pages in a structured output directory. ## Quick Start Create a knowledge comic about Alan Turing's life using the ohmsha preset, 10 pages, portrait aspect ratio, in Chinese.

Frequently Asked Questions about baoyu-comic

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an educational comic from an article or topic?

Provide the source content as text, a file path, a URL, or just a topic, and optionally specify art style, tone, layout, and language. The skill analyzes the content, confirms style options with you, builds a storyboard and characters, writes prompts, and generates each page image.

What art styles and tones are available for comic generation?

Six art styles (ligne-claire, manga, realistic, ink-brush, chalk, minimalist) combine with seven tones (neutral, warm, dramatic, romantic, energetic, vintage, action). Five presets like ohmsha and wuxia add special rules beyond plain art plus tone combinations.

Can I generate only a storyboard without images?

Yes, partial workflows support storyboard-only, prompts-only, images-only, and regenerating specific pages by number. Trigger them with natural language such as "just the storyboard" or "regenerate page 3".

How does the comic keep characters consistent across pages?

Character consistency relies on detailed text descriptions in characters/characters.md embedded inline into every page prompt, because the image generation tool accepts only text prompts. An optional character sheet PNG is produced as a human review artifact, not as model input.

Why did my generated comic pages end up in the wrong directory?

This happens when curl downloads use relative output paths and the shell working directory drifts between batches. Always pass a fully qualified absolute path to curl -o and verify each downloaded PNG exists and is non-empty before continuing.